< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 25 in Layer 20

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')



Text #0

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.8661. Min Act: -0.1700

Data Index: 10073563 (The Pile)

Max Activating Token Index: 385

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.8348. Min Act: -0.1700

Data Index: 1010503 (The Pile)

Max Activating Token Index: 520

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.7722. Min Act: -0.1700

Data Index: 1499482 (The Pile)

Max Activating Token Index: 926

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.7409. Min Act: -0.1700

Data Index: 7327950 (The Pile)

Max Activating Token Index: 189

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.7409. Min Act: -0.1700

Data Index: 1259151 (The Pile)

Max Activating Token Index: 1009

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.7409. Min Act: -0.1700

Data Index: 10444952 (The Pile)

Max Activating Token Index: 110

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.7253. Min Act: -0.1700

Data Index: 5837817 (The Pile)

Max Activating Token Index: 644

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.7096. Min Act: -0.1700

Data Index: 9737659 (The Pile)

Max Activating Token Index: 927

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.6940. Min Act: -0.1700

Data Index: 7790066 (The Pile)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.6940. Min Act: -0.1700

Data Index: 10515394 (The Pile)

Max Activating Token Index: 26

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.6940. Min Act: -0.1700

Data Index: 3913534 (The Pile)

Max Activating Token Index: 378

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.6783. Min Act: -0.1700

Data Index: 54835 (The Pile)

Max Activating Token Index: 590

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.6627. Min Act: -0.1700

Data Index: 4425934 (The Pile)

Max Activating Token Index: 493

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.6627. Min Act: -0.1700

Data Index: 7579027 (The Pile)

Max Activating Token Index: 828

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.6627. Min Act: -0.1700

Data Index: 349873 (The Pile)

Max Activating Token Index: 337

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.6627. Min Act: -0.1700

Data Index: 6275192 (The Pile)

Max Activating Token Index: 152

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.6627. Min Act: -0.1700

Data Index: 8730524 (The Pile)

Max Activating Token Index: 62

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.6627. Min Act: -0.1700

Data Index: 6959213 (The Pile)

Max Activating Token Index: 835

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.6627. Min Act: -0.1700

Data Index: 9804496 (The Pile)

Max Activating Token Index: 528

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.6470. Min Act: -0.1700

Data Index: 5010317 (The Pile)

Max Activating Token Index: 596

Click toggle to see full text

Truncated

Full Text #19